Datasets for Data-Driven Reinforcement Learning

By Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine. 2020

5 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Sergey Levine
2. Shixiang Shane Gu
3. Shimon Whiteson
4. Ofir Nachum
5. Dale Schuurmans
6. Phillip Swazinna
7. Seyed Kamyar Seyed Ghasemipour
8. Tabish Rashid

Citations in the corpus

• EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL (2020, methodology): “We note that with our proposed autoregressive models, the re-sults for BCQ and BEAR are equal to or improved upon the values reported in the D4RL benchmark (Fu et al., 2020b) (green horizontal lines).”
• Imitating Human Behaviour with Diffusion Models (2023, background): “This environment has become a popular offline RL benchmark for learning reward-maximising policies (Fu et al., 2020).”
• Overcoming Model Bias for Robust Offline Deep Reinforcement Learning (2020, background): “"= f0:0;0:2;0:4;0:6;0:8;1:0g. Altogether, these settings allow us to inspect the performance of our algorithm in the face of various issues encountered in real-world offline RL problems, such as (Fu et al. 2020) undirected and multitask data (the bad baseline is certainly not optimizing any of t”